def train(self, trainSet: InstanceList, parameters: Parameter):
"""
Training algorithm for the linear discriminant analysis classifier (Introduction to Machine Learning, Alpaydin,
2015).
PARAMETERS
----------
trainSet : InstanceList
Training data given to the algorithm.
parameters : Parameter
Parameter of the Lda algorithm.
"""
w0 = {}
w = {}
priorDistribution = trainSet.classDistribution()
classLists = Partition(trainSet)
covariance = Matrix(trainSet.get(0).continuousAttributeSize(), trainSet.get(0).continuousAttributeSize())
for i in range(classLists.size()):
averageVector = Vector(classLists.get(i).continuousAverage())
classCovariance = classLists.get(i).covariance(averageVector)
classCovariance.multiplyWithConstant(classLists.get(i).size() - 1)
covariance.add(classCovariance)
covariance.divideByConstant(trainSet.size() - classLists.size())
covariance.inverse()
for i in range(classLists.size()):
Ci = classLists.get(i).getClassLabel()
averageVector = Vector(classLists.get(i).continuousAverage())
wi = covariance.multiplyWithVectorFromRight(averageVector)
w[Ci] = wi
w0i = -0.5 * wi.dotProduct(averageVector) + math.log(priorDistribution.getProbability(Ci))
w0[Ci] = w0i
self.model = LdaModel(priorDistribution, w, w0)
def train(self, trainSet: InstanceList, parameters: Parameter):
"""
Training algorithm for the quadratic discriminant analysis classifier (Introduction to Machine Learning,
Alpaydin, 2015).
PARAMETERS
----------
trainSet : InstanceList
Training data given to the algorithm.
"""
w0 = {}
w = {}
W = {}
classLists = Partition(trainSet)
priorDistribution = trainSet.classDistribution()
for i in range(classLists.size()):
Ci = classLists.get(i).getClassLabel()
averageVector = Vector(classLists.get(i).continuousAverage())
classCovariance = classLists.get(i).covariance(averageVector)
determinant = classCovariance.determinant()
classCovariance.inverse()
Wi = deepcopy(classCovariance)
Wi.multiplyWithConstant(-0.5)
W[Ci] = Wi
wi = classCovariance.multiplyWithVectorFromLeft(averageVector)
w[Ci] = wi
w0i = -0.5 * (wi.dotProduct(averageVector) + math.log(determinant)) + math.log(priorDistribution.
getProbability(Ci))
w0[Ci] = w0i
self.model = QdaModel(priorDistribution, W, w, w0)
def train(self, trainSet: InstanceList, parameters: KMeansParameter):
priorDistribution = trainSet.classDistribution()
classMeans = InstanceList()
classLists = Partition(trainSet)
for i in range(classLists.size()):
classMeans.add(classLists.get(i).average())
self.model = KMeansModel(priorDistribution, classMeans,
parameters.getDistanceMetric())